Detecting Alarming Student Verbal Responses using Text and Audio Classifier
For educators and safety systems, this work provides a method to expedite human review of potentially concerning student verbal responses, which could be life-saving in timely intervention scenarios.
The paper addresses a safety gap in Automated Verbal Response Scoring by proposing a hybrid framework that combines text and audio classifiers to detect alarming student responses, achieving enhanced performance over traditional systems.
This paper addresses a critical safety gap in the use Automated Verbal Response Scoring (AVRS). We present a novel hybrid framework for troubled student detection that combines a text classifier, trained to detect responses based on their content, and an audio classifier, trained to detect responses using prosodic markers. This approach overcomes key limitations of traditional AVRS systems by considering both content and prosody of responses, achieving enhanced performance in identifying potentially concerning responses. This system can expedite the review process by humans, which can be life-saving particularly when timely intervention may be crucial.